Filters








4,037 Hits in 5.7 sec

USE OF DEEP LEARNING TO ANALYSE AND EXPLOIT MOLECULAR DATA

D.A Landau
2021 Hematological Oncology  
Landau will review key concepts in ML, including devising appropriate background models, developing diagnostics and metrics of success for methods optimization, and critical factors for building robust  ...  Furthermore, the calibrated qualities and the number of discrete pixels in a digital slide allow automated image analysis and quantification by using computer vision and, in particular, deep learning approaches  ... 
doi:10.1002/hon.9_2879 fatcat:jpc6yguirnb6rnctncjkucwtvm

ARTIFICIAL INTELLIGENCE AND PATHOLOGY

P Brousset
2021 Hematological Oncology  
are also new methodologies able to analyze texts and extract information automatically, thus allowing the integration of information of different nature and type, but also techniques usefull to manage uncertainty  ...  In this talk we focus on the recent trends and successes of artificial intelligence in the medical field, with practical examples in which artificial intelligence supports physicians in their work, without  ...  Landau will review key concepts in ML, including devising appropriate background models, developing diagnostics and metrics of success for methods optimization, and critical factors for building robust  ... 
doi:10.1002/hon.8_2879 fatcat:w2xc6heruzf6pg4vgavn23ufre

An uncertainty-aware, shareable, and transparent neural network architecture for brain-age modeling

Tim Hahn, Jan Ernsting, Nils R. Winter, Vincent Holstein, Ramona Leenings, Marie Beisemann, Lukas Fisch, Kelvin Sarink, Daniel Emden, Nils Opel, Ronny Redlich, Jonathan Repple (+21 others)
2022 Science Advances  
analyses.  ...  In contrast to currently used algorithms-which either do not provide uncertainty estimates or over-or underestimate uncertaintythe MCCQR model provides robust, distribution-free uncertainty quantification  ...  Principal investigators (PIs) with respective areas of responsibility in the FOR2107 consortium are as follows: Work Package WP1, FOR2107/MACS cohort and brain imaging: T.  ... 
doi:10.1126/sciadv.abg9471 pmid:34985964 pmcid:PMC8730629 fatcat:zeupkpspqjahfptcixzbz6rt3a

An Uncertainty-Aware, Shareable and Transparent Neural Network Architecture for Brain-Age Modeling [article]

Tim Hahn, Jan Ernsting, Nils R. Winter, Vincent Holstein, Ramona Leenings, Marie Beisemann, Lukas Fisch, Kelvin Sarink, Daniel Emden, Nils Opel, Ronny Redlich, Jonathan Repple (+22 others)
2021 arXiv   pre-print
The MCCQR model provides robust, distribution-free uncertainty quantification in high-dimensional neuroimaging data, achieving lower error rates compared to existing models across ten recruitment centers  ...  However, Machine Learning models underlying the field do not consider uncertainty, thereby confounding results with training data density and variability.  ...  The analysis was conducted with data from the German National Cohort (GNC) (www.nako.de).  ... 
arXiv:2107.07977v1 fatcat:fdx6dgeahba2xmc3ik7hvzemou

Uncertainty quantification in subject-specific estimation of local vessel mechanical properties [article]

Bruno V Rego, Dar Weiss, Matthew R Bersi, Jay D Humphrey
2021 bioRxiv   pre-print
associated with local point estimates of mechanical properties.  ...  In the present study, we have integrated a novel uncertainty quantification and propagation pipeline within our inverse modeling approach, relying on empirical and analytic Bayesian techniques.  ...  METHODS Summary of approach Herein, we augment previously established procedures for mechanical testing, high-resolution imaging, and inverse modeling with a new integrated workflow for uncertainty quantification  ... 
doi:10.1101/2021.08.02.454803 fatcat:tw2dk6ycuna5lnydt2d4gwssve

A Contrast-Enhanced Computed Tomography Based Radiomics Approach for Preoperative Differentiation of Pancreatic Cystic Neoplasm Subtypes: A Feasibility Study

Xiaoyong Shen, Fan Yang, Pengfei Yang, Modan Yang, Lei Xu, Jianyong Zhuo, Jianguo Wang, Di Lu, Zhikun Liu, Shu-sen Zheng, Tianye Niu, Xiao Xu
2020 Frontiers in Oncology  
Methods: This study enrolled 164 patients including 76 with SCA, 40 with MCN and 48 with IPMN. Patients were randomly split into a training cohort (n = 115) and validation cohort (n = 41).  ...  Due to the potential of malignant-transforming, patients with MCN and IPMN require radical surgery while patients with SCA need periodic surveillance.  ...  It is important to screen radiomics features that are robust against tumor segmentation uncertainty.  ... 
doi:10.3389/fonc.2020.00248 pmid:32185129 pmcid:PMC7058789 fatcat:lcfslr6zv5g2nfcrfkoqhzyoty

Combining radiomic features with a miRNA classifier may improve prediction of malignant pathology for pancreatic intraductal papillary mucinous neoplasms

Jennifer B. Permuth, Jung Choi, Yoganand Balarunathan, Jongphil Kim, Dung-Tsa Chen, Lu Chen, Sonia Orcutt, Matthew P. Doepker, Kenneth Gage, Geoffrey Zhang, Kujtim Latifi, Sarah Hoffe (+10 others)
2016 OncoTarget  
Using a retrospective cohort of 38 surgically-resected, pathologically-confirmed IPMNs (20 benign; 18 malignant) with preoperative computed tomography (CT) images and matched plasma-based 'miRNA genomic  ...  Evaluation of uncertainty by 10-fold cross-validation retained an AUC>0.80 (0.87 (95% CI:0.84-0.89)).  ...  Cross-validation and correlative analysis Evaluation of uncertainty by 10-fold cross-validation showed robust estimates of diagnostic performance with AUC above 0.75 for most models (Supplementary Table  ... 
doi:10.18632/oncotarget.11768 pmid:27589689 pmcid:PMC5349874 fatcat:dln6zqpfxvgzreotf6kie6vtxu

Counting the platelets: a robust and sensitive quantification method for thrombus formation

Tomas Lindahl, Lars Faxälv, Kjersti Claesson
2016 Thrombosis and Haemostasis  
In conclusion, quantification of thrombus formation by platelet count is a sensitive and robust method that enables measurement of platelet accumulation and platelet stability in an absolute scale that  ...  Five percent of the platelets were fluorescently labelled and z-stack time-lapse images were captured during thrombus formation.  ...  Figure 6 . 6 Method robustness of confocal volume estimation and platlet count quantification.  ... 
doi:10.1160/th15-10-0799 pmid:26842994 fatcat:brq732l3bvf5xnmaaihwv3cmm4

ARTIFICIAL INTELLIGENCE AND MEDICINE: PAST AND FUTURE

L.M Gambardella
2021 Hematological Oncology  
When considering ctDNA quantity, both pre-and on-treatment levels were prognostic for PFS, with higher levels correlating with adverse outcome (Pre-LD [HR = 1.5, CI = 1.1-1.9], Day 0 [HR = 1.6, CI = 1.2  ...  Landau will review key concepts in ML, including devising appropriate background models, developing diagnostics and metrics of success for methods optimization, and critical factors for building robust  ...  Furthermore, the calibrated qualities and the number of discrete pixels in a digital slide allow automated image analysis and quantification by using computer vision and, in particular, deep learning approaches  ... 
doi:10.1002/hon.7_2879 fatcat:csptrct755dnfbyrcvwffjjjkq

TREM2 Haplodeficiency in Mice and Humans Impairs the Microglia Barrier Function Leading to Decreased Amyloid Compaction and Severe Axonal Dystrophy

Peng Yuan, Carlo Condello, C. Dirk Keene, Yaming Wang, Thomas D. Bird, Steven M. Paul, Wenjie Luo, Marco Colonna, David Baddeley, Jaime Grutzendler
2016 Neuron  
This led to an increase in less compact plaques with longer and branched amyloid fibrils resulting in greater surface exposure to adjacent neurites. This was associated with more severe neuritic tau §  ...  In Trem2 or DAP12 haplodeficient mice and in humans with R47H TREM2 mutations, microglia had a markedly reduced ability to envelop amyloid deposits.  ...  For all analyses, tiled imaging using a motorized stage was used to image across one cerebral hemisphere in mice.  ... 
doi:10.1016/j.neuron.2016.05.003 pmid:27196974 pmcid:PMC4898967 fatcat:uqasvcnisfan3lesp635vvf2fq

Human tissue in systems medicine

Peter D. Caie, Klaas Schuur, Anca Oniscu, Peter Mullen, Paul A. Reynolds, David J. Harrison
2013 The FEBS Journal  
In this short review we argue that a systems medicine approach to pathology will not seek to replace traditional pathology, but rather augment it.  ...  Histopathology, the examination of an architecturally artefactual, twodimensional and static image remains a potent tool allowing diagnosis and empirical expectation of prognosis.  ...  Pathology is and should be robust in a modelling sense.  ... 
doi:10.1111/febs.12550 pmid:24118991 fatcat:ch6mh6ll3rdenbg2bibmhazl2i

Method of Tumor Pathological Micronecrosis Quantification via Deep Learning from Label Fuzzy Proportions

Qiancheng Ye, Qi Zhang, Yu Tian, Tianshu Zhou, Hongbin Ge, Jiajun Wu, Na Lu, Xueli Bai, Tingbo Liang, Jingsong Li
2021 IEEE journal of biomedical and health informatics  
The presence of necrosis is associated with tumor progression and patient outcomes in many cancers, but existing analyses rarely adopt quantitative methods because the manual quantification of histopathological  ...  We aim to accurately identify necrotic regions on hematoxylin and eosin (HE)stained slides and to calculate the ratio of necrosis with minimal annotations on the images.  ...  Along with pathological features such as necrosis, other clinical factors relating to the prognosis of cancer patients can be integrated to build a more comprehensive prognostic model, since the quantification  ... 
doi:10.1109/jbhi.2021.3071276 pmid:33822729 fatcat:xscekjqt7bacbjxzpmlq5mo25q

A framework for optimal whole-sample histological quantification of neurite orientation dispersion in the human spinal cord

Francesco Grussu, Torben Schneider, Richard L. Yates, Hui Zhang, Claudia A.M. Gandini Wheeler-Kingshott, Gabriele C. DeLuca, Daniel C. Alexander
2016 Journal of Neuroscience Methods  
Results: Palmgren's silver staining of sagittal spinal cord sections provides robust visualisation of neuronal elements, enabling OD quantification.  ...  The choice of spatial scale of ST analysis influences OD values, and weighted directional statistics provide OD maps with high contrast-to-noise.  ...  Acknowledgements The authors are thankful to Dr Jonathan Clayden, Dr Bernard Siow, Professor John Ashburner and Professor Sune Jespersen for useful discussion; to Ms Janis Carter for help with histology  ... 
doi:10.1016/j.jneumeth.2016.08.002 pmid:27497747 fatcat:5snnoxkdcrcdfajnkamuj247p4

DBCal: Density Based Calibration of classifier predictions for uncertainty quantification [article]

Alex Hagen, Karl Pazdernik, Nicole LaHaye, Marjolein Oostrom
2022 arXiv   pre-print
probability that the outputs of two neural networks are correct by showing an expected calibration error of less than 0.2% on a binary classifier, and less than 3% on a semantic segmentation network with  ...  We empirically show that the uncertainty returned by our method is an accurate measurement of the probability that the classifier's prediction is correct and, therefore has broad utility in uncertainty  ...  Drawing from other computational sciences, we posit that current uncertainty quantification techniques are more similar to "verification" or "perturbation analyses" [18] , in that they measure values  ... 
arXiv:2204.00150v1 fatcat:b7gwftzvjnhrfh35xlb63uszwi

Uncertain-DeepSSM: From Images to Probabilistic Shape Models [article]

Jadie Adams, Riddhish Bhalodia, Shireen Elhabian
2020 arXiv   pre-print
DeepSSM is an end-to-end deep learning approach that extracts statistical shape representation directly from unsegmented images with little manual overhead.  ...  uncertainty via a Monte Carlo dropout sampling to approximate a variational distribution over the network parameters.  ...  Uncertain-DeepSSM quantifies granular estimates of uncertainty with respect to a low-dimensional shape descriptor to provide spatiallycoherent, localized uncertainty measures (see Fig. 1 ) that are robust  ... 
arXiv:2007.06516v1 fatcat:ujievb3tgnf3fmo6pgyzai2v6a
« Previous Showing results 1 — 15 out of 4,037 results